An Empirical Study on Google Research Football Multi-agent Scenarios

TL;DR

This paper presents a comprehensive empirical study on multi-agent reinforcement learning in Google Research Football, introducing a new training pipeline, open-source framework, and benchmarks to advance research in full-game scenarios.

Contribution

It provides a population-based training pipeline, open-source framework, and benchmark results for multi-agent football scenarios, filling a gap in existing research and tools.

Findings

Outperforms difficulty 1.0 bots within 2 million steps

Provides a reference for Independent Proximal Policy Optimization (IPPO) performance

Open-sources training framework Light-MALib with analytical tools

Abstract

Few multi-agent reinforcement learning (MARL) research on Google Research Football (GRF) focus on the 11v11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been released to the public. In this work, we fill the gap by providing a population-based MARL training pipeline and hyperparameter settings on multi-agent football scenario that outperforms the bot with difficulty 1.0 from scratch within 2 million steps. Our experiments serve as a reference for the expected performance of Independent Proximal Policy Optimization (IPPO), a state-of-the-art multi-agent reinforcement learning algorithm where each agent tries to maximize its own policy independently across various training configurations. Meanwhile, we open-source our training framework Light-MALib which extends the MALib codebase by distributed and asynchronized implementation with additional analytical tools for football games. Finally, we provide guidance for building strong football AI with population-based training and release diverse pretrained policies for benchmarking. The goal is to provide the community with a head start for whoever experiment their works on GRF and a simple-to-use population-based training framework for further improving their agents through self-play. The implementation is available at https://github.com/Shanghai-Digital-Brain-Laboratory/DB-Football.